Deep Image Compression Using Scene Text Quality Assessment
This addresses the issue of unreadable text in compressed images for Internet communication engineering, representing an incremental improvement in domain-specific image compression.
The paper tackled the problem of text quality degradation in compressed images by proposing a compression method that maintains text quality using a scene text image quality assessment model, with results showing superiority over existing methods in objective and subjective evaluations.
Image compression is a fundamental technology for Internet communication engineering. However, a high compression rate with general methods may degrade images, resulting in unreadable texts. In this paper, we propose an image compression method for maintaining text quality. We developed a scene text image quality assessment model to assess text quality in compressed images. The assessment model iteratively searches for the best-compressed image holding high-quality text. Objective and subjective results showed that the proposed method was superior to existing methods. Furthermore, the proposed assessment model outperformed other deep-learning regression models.